A Vertex Similarity Index Using Community Information to Improve Link Prediction Accuracy

Link prediction plays an important role in complex network analysis. It is to predict the existence of an unknown link or a future link in a network. Classical methods for link prediction evaluate the similarity of vertices based on common neighbors, and denote that every common neighbor makes equal contribution to the connection likelihood. However, common neighbors may play different roles depending on whether they belong to the same community, where vertices are densely or sparsely connected to other communities. This paper proposes a novel similarity index for link prediction which combines the topology information and community information. The proposed approach is compared with ten classical local similarity indices on ten real-world networks. The experiment results shown that the proposed approach can improve the accuracy of link prediction no matter which community detection algorithm is used.